// features created from the word text like character ngrams
this.entityFeatureExtractors = Arrays.asList(
new CoveredTextExtractor(),
//new TypePathExtractor(IdentifiedAnnotation.class, "stem"),
new ProliferatingExtractor(
new SpannedTextExtractor(),
new LowerCaseProliferator(),
new CapitalTypeProliferator(),
new NumericTypeProliferator(),
new CharacterNGramProliferator(fromRight, 0, 2),
new CharacterNGramProliferator(fromRight, 0, 3)));
// a list of feature extractors that require the token and the sentence
this.contextFeatureExtractors = new ArrayList<ContextExtractor<IdentifiedAnnotation>>();
this.contextFeatureExtractors.add(new ContextExtractor<IdentifiedAnnotation>(
IdentifiedAnnotation.class,
new CoveredTextExtractor(),
//new TypePathExtractor(IdentifiedAnnotation.class, "stem"),
new Preceding(2),
new Following(2)));
ContextExtractor<BaseToken> tokenContextExtractor1 = new ContextExtractor<BaseToken>(
BaseToken.class,
new SpannedTextExtractor(),
new ContextExtractor.Ngram(new Covered()),
new ContextExtractor.Ngram(new Preceding(1)),
new ContextExtractor.Ngram(new Preceding(2)),
//new ContextExtractor.Ngram(new Preceding(1, 2)),